© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 3506
    Prev
    Next
    INDEX
    Explanations

    phrases related to research and development activities

    oai_token-act-pair · gpt-3.5-turbo

    references to research and development as well as their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iguous
    -0.76
    lus
    -0.73
    κ
    -0.71
     Rivers
    -0.69
     Hig
    -0.67
    tops
    -0.65
    ãĥĥãĥī
    -0.65
    pour
    -0.64
    wic
    -0.63
    auga
    -0.63
    POSITIVE LOGITS
     evaluation
    1.35
     experimentation
    1.33
     development
    1.19
     analysis
    1.17
     dissemination
    1.15
     refinement
    1.09
     certification
    1.05
     advocacy
    1.05
     observation
    1.04
     prosecution
    1.04
    Activations Density 0.154%

    No Known Activations